LLM·Dex
Newsletter

Command R+ (08-2024) vs Mistral Medium

A complete head-to-head: pricing, context window, benchmarks, modality coverage, and openness, with a programmatic verdict synthesized from the underlying data.

Updated

Command R+ (08-2024) specs · Mistral Medium specs
Verdict by category
  • PriceMistral Medium

    Mistral Medium is roughly 5.0× cheaper on output tokens ($2.00 vs $10.00 per 1M).

  • Context windowTie

    Both ship a 128K-token context window.

  • BenchmarksTie

    No directly comparable public benchmarks are available for both models, check the spec sheets for individual scores.

  • ModalitiesTie

    Both handle text.

  • OpennessCommand R+ (08-2024)

    Command R+ (08-2024) ships open weights (CC-BY-NC 4.0); Mistral Medium is API-only.

It's a genuine coin-flip between Command R+ (08-2024) and Mistral Medium: 1 category wins each, with the rest tied. Mistral Medium is roughly 5.0× cheaper on output tokens ($2.00 vs $10.00 per 1M). Both ship a 128K-token context window.

No directly comparable public benchmarks are available for both models, check the spec sheets for individual scores. Both target the same set of modalities (text), so the deciding factors are price, context, and raw quality. Command R+ (08-2024) ships open weights (CC-BY-NC 4.0); Mistral Medium is API-only.

Mistral Medium is the newer of the two, released 4 months after Command R+ (08-2024), which usually means a more recent knowledge cutoff and updated safety post-training. Command R+ (08-2024) is usually picked for rag and data extraction workloads, while Mistral Medium sees more deployments in customer support and chatbots. If pricing matters more than every last benchmark point, run the numbers in the calculator below before committing.

Side-by-side specs

SpecCommand R+ (08-2024)Mistral Medium
ProviderCohereMistral
ReleasedAug 2024Dec 2024
Modalitiestexttext
Context window128K tokens128K tokens
Max output,,
Input · 1M$2.50 / 1M tokens$0.40 / 1M tokens
Output · 1M$10.00 / 1M tokens$2.00 / 1M tokens
Knowledge cutoff,,
Open weightsYes (CC-BY-NC 4.0)No
API availableYesYes

Pricing at scale

What you'd actually pay at typical workloads. Numbers come from each model's published per-million-token rates.

  • Light usage, 100k in / 50k out per day$22.50 vs $4.20
  • Heavy usage, 1M in / 500k out per day$225 vs $42.00
  • RAG workload, 5M in / 200k out per day$435 vs $72.00

Light usage, 100k in / 50k out per day: $22.50 vs $4.20 per month, model B comes out ahead. Heavy usage, 1M in / 500k out per day: $225 vs $42.00 per month, model B comes out ahead. RAG workload, 5M in / 200k out per day: $435 vs $72.00 per month, model B comes out ahead.

Price calculator

Estimated spend for the listed models at your usage. Numbers are derived from each model's published per-million-token rates.

  • Command R+ (08-2024)$0.750
  • Mistral Medium$0.140

Benchmarks compared

Only sourced numbers. Where a benchmark is missing for one model we show the available value rather than fabricating the other.

Command R+ (08-2024)Mistral Medium
  • MMLU75.7
Pick Command R+ (08-2024) if

Command R+ (08-2024) fits when…

  • RAG-tuned
  • Citation generation
  • Enterprise tooling
  • Self-hosting and on-prem requirements, open weights (CC-BY-NC 4.0).
Pick Mistral Medium if

Mistral Medium fits when…

  • Mid-tier balance
  • EU-friendly
  • Cost-sensitive workloads, 5.0× cheaper than Command R+ (08-2024) on output tokens.
Don't want either?

Consider Command R

Cohere's mid-tier RAG-optimized model, affordable and reliable on retrieval workloads.

See Command R specsCommand R+ (08-2024) vs Command RMistral Medium vs Command R

Frequently asked

  • Is Command R+ (08-2024) or Mistral Medium cheaper?
    Mistral Medium is cheaper at $2.00 / 1M tokens per million output tokens, vs $10.00 / 1M tokens for Command R+ (08-2024).
  • Which has the larger context window?
    Both Command R+ (08-2024) and Mistral Medium ship a 128K-token context window.
  • Is Command R+ (08-2024) or Mistral Medium better for coding?
    Both Command R+ (08-2024) and Mistral Medium are competitive on coding benchmarks. See each model's individual spec page for HumanEval and SWE-bench scores where published. For an opinionated pick, consult our Best LLM for Coding ranking.
  • Are either of these models open source?
    Command R+ (08-2024) ships open weights (CC-BY-NC 4.0). Mistral Medium is API-only.
  • When were Command R+ (08-2024) and Mistral Medium released?
    Command R+ (08-2024) was released by Cohere on 2024-08-30. Mistral Medium was released by Mistral on 2024-12-18.
Friday digest

The week's AI launches, in your inbox.

One short email every Friday, new models, leaks, and quietly-shipped APIs you missed.